SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations
Abstract: Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly complicated forward/reverse processes, so they are not suitable for resource-limited settings. To solving this problem, learning a simpler process is gathering much attention currently. We present an enhanced GAN-based denoising method, called SPI-GAN, using our proposed straight-path interpolation definition. To this end, we propose a GAN architecture i) denoising through the straight-path and ii) characterized by a continuous mapping neural network for imitating the denoising path. This approach drastically reduces the sampling time while achieving as high sampling quality and diversity as SGMs. As a result, SPI-GAN is one of the best-balanced models among the sampling quality, diversity, and time for CIFAR-10, and CelebA-HQ-256.
- Neural ordinary differential equations. Advances in neural information processing systems, 31, 2018.
- Image generation with shortest path diffusion. arXiv preprint arXiv:2306.00501, 2023.
- A family of embedded runge-kutta formulae. Journal of Computational and Applied Mathematics, 6(1):19 – 26, 1980.
- Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873–12883, 2021.
- Learning energy-based models by diffusion recovery likelihood. arXiv preprint arXiv:2012.08125, 2021.
- Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
- Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
- Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2018.
- Training generative adversarial networks with limited data. Advances in Neural Information Processing Systems, 33:12104–12114, 2020a.
- Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 8110–8119, 2020b.
- Neural controlled differential equations for irregular time series. In NeurIPS, 2020.
- On fast sampling of diffusion probabilistic models. arXiv preprint arXiv:2106.00132, 2021.
- The cifar-10 dataset. online: http://www. cs. toronto. edu/kriz/cifar. html, 55(5), 2014.
- Improved precision and recall metric for assessing generative models. Advances in Neural Information Processing Systems, 32, 2019.
- Improved denoising diffusion probabilistic models. In International Conference on Machine Learning, pp. 8162–8171. PMLR, 2021.
- Dual contradistinctive generative autoencoder. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 823–832, 2021.
- Adversarial latent autoencoders. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14104–14113, 2020.
- Improved techniques for training gans. Advances in neural information processing systems, 29, 2016.
- Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502, 2021a.
- Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems, 32, 2019.
- Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2021b.
- Score-based generative modeling in latent space. Advances in Neural Information Processing Systems, 34, 2021.
- Diffusion-gan: Training gans with diffusion. arXiv preprint arXiv:2206.02262, 2022.
- Tackling the generative learning trilemma with denoising diffusion gans. arXiv preprint arXiv:2112.07804, 2021.
- Differentiable augmentation for data-efficient gan training. Advances in Neural Information Processing Systems, 33:7559–7570, 2020.
Paper Prompts
Sign up for free to create and run prompts on this paper.